© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94909
    Prev
    Next
    INDEX
    Explanations

    terms related to telecommunication and technology applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edor
    -0.07
    asel
    -0.07
    gia
    -0.07
     cong
    -0.07
    enis
    -0.07
    ladu
    -0.07
    uste
    -0.06
    PASS
    -0.06
    ltk
    -0.06
    metic
    -0.06
    POSITIVE LOGITS
    773
    0.07
    ington
    0.06
    INGTON
    0.06
     TMPro
    0.06
     circular
    0.06
     Circular
    0.06
     bounding
    0.06
    564
    0.06
    PLE
    0.05
     Stat
    0.05
    Activations Density 0.087%

    No Known Activations